A radically new approach to statistical modelling, which combines mathematical techniques
of Bayesian statistics with the philosophy of the theory of competitive on‐line algorithms, has …

Multi-armed bandits a simple but very powerful framework for algorithms that make
decisions over time under uncertainty. An enormous body of work has accumulated over the …

We consider the setting of sequential prediction of arbitrary sequences based on specialized
experts. We first provide a review of the relevant literature and present two theoretical …

The problem of classification has been widely studied in the data mining, machine learning,
database, and information retrieval communities with applications in a number of diverse …

This important text and reference for researchers and students in machine learning, game
theory, statistics and information theory offers a comprehensive treatment of the problem of …

We describe several improvements to Freund and Schapire's AdaBoost boosting algorithm,
particularly in a setting in which hypotheses may assign confidences to each of their …

When trying to learn a model for the prediction of an outcome given a set of covariates, a
statistician has many estimation procedures in their toolbox. A few examples of these …

This work focuses on algorithms which learn from examples to perform multiclass text and
speech categorization tasks. Our approach is based on a new and improved family of …

In an online decision problem, one makes a sequence of decisions without knowledge of the
future. Each period, one pays a cost based on the decision and observed state. We give a …

PAC-Bayesian learning methods combine the informative priors of Bayesian methods with
distribution-free PAC guarantees. Building on earlier methods for PAC-Bayesian model …